An Empirical Research of Multi-Classifier Fusion Methods and Diversity Measure in Remote Sensing Classification

Hongchao Ma; Wei Zhou; Xinyi Dong; Honggen Xu

1st International ICST Workshop on Knowledge Discovery and Data Mining

Research Article

An Empirical Research of Multi-Classifier Fusion Methods and Diversity Measure in Remote Sensing Classification

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/wkdd.2008.2731,
    author={Hongchao Ma and Wei Zhou and Xinyi Dong and Honggen Xu},
    title={An Empirical Research of Multi-Classifier Fusion Methods and Diversity Measure in Remote Sensing Classification},
    proceedings={1st International ICST Workshop on Knowledge Discovery and Data Mining},
    publisher={ACM},
    proceedings_a={WKDD},
    year={2010},
    month={5},
    keywords={},
    doi={10.4108/wkdd.2008.2731}
}

Hongchao Ma
Wei Zhou
Xinyi Dong
Honggen Xu
Year: 2010
An Empirical Research of Multi-Classifier Fusion Methods and Diversity Measure in Remote Sensing Classification
WKDD
ACM
DOI: 10.4108/wkdd.2008.2731

Hongchao Ma¹, Wei Zhou¹^,*, Xinyi Dong², Honggen Xu¹

1: SRSAIE, Wuhan Univ. Wuhan Hubei, 430079, China
2: LIESMARS, Wuhan Univ. Wuhan Hubei, 430079, China

*Contact email: zhouwei_prc@yahoo.com.cn

Abstract

In this paper, Multi-Classifier System (MCS) is applied to the automatic classification of remote sensing images, and some effective multi-classifier fusion methods with relatively high accuracy are proposed based on substantive experiments. The classification accuracy of MCS has been remarkably improved compared to single classifier with an average increment of 5%. In addition, a diversity measure named EPD is presented, and the paper proves that its ability in predicting the performance of classifiers combining can be used to assist the construction of multiple classifier systems.

Published: 2010-05-16
Publisher: ACM
Modified: 2010-05-16

: http://dx.doi.org/10.4108/wkdd.2008.2731